Claude Second Opinion

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description fully discloses behavioral traits: Claude is instructed to find flaws, assumptions, missed edge cases; it never modifies files; it explains the result format (JSON vs prose) and how to parse the footer. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is comprehensive but slightly lengthy; however, every sentence provides essential information (purpose, usage, result format). It is well front-loaded with the core function and structured logically. Could be marginally trimmed but is effective.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (5 parameters, no output schema), the description covers all necessary aspects: how to invoke, what to expect in return, how to handle different result formats, and even how to continue sessions. It prepares the agent for both JSON and prose responses, ensuring complete usability.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents each parameter. The description adds value by explaining the adversarial purpose, the importance of providing full reasoning, and how session_id/workspace_dir are used for continuity. This extra context elevates it above baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides an adversarial review of the user's own analysis, explicitly distinguishing it from siblings like ask_claude and claude_debate_open by emphasizing it hunts for flaws rather than agrees. It also specifies it never modifies files, reinforcing its unique role.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit guidance on when to use (risky changes, migrations, security-sensitive edits, low confidence) and how to integrate with sub-agents. It contrasts with other tools by positioning itself as an independent cross-model reviewer, and explains when to treat disagreements as high-signal.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.